PhD in Biostatistics from the University Montpellier I - Philippe Saint

URL : http ://stpierre31.free.fr ... PhD thesis in Biostatistics, defended on the 29th April 2005. ... Word, Excel, Powerpoint, LATEX, Scientific workplace, Winedit.
Télécharger le PDF
465KB taille 7 téléchargements 282 vues
commentaire
Report
SAINT PIERRE Philippe 962, Av. Louis Ravas, Bat. B, Appt. 17 34080 MONTPELLIER FRANCE Tel : +33.4.67.02.05.95

Date of birth : 01/09/78 Single Nationality : French

e-mail : [email protected] URL : http ://stpierre31.free.fr

PhD in Biostatistics from the University Montpellier I Academic Degrees Sep 2005/ ...

Post-doctoral position in Biostatistics, University Institute of Clinical Research, Montpellier, France.

2002/April 2005

PhD thesis in Biostatistics, defended on the 29th April 2005. Advisors : Profs. J-P Daurès and P. Godard. University Institute of Clinical Research, University Montpellier I, France. Title : Multi-states Markov models and application to asthma.

2000/June 2001

Research Master Degree in Applied Mathematics, with honors. Option Probability-Statistic. University Paul Sabatier, Toulouse III, France. Lessons : -

1999/June 2000 1998/June 1999

Large deviations and applications with M. Ledoux. Asymptotic statistic with F. Gamboa. Functional statistic with F. Ferraty and P. Vieu. Statistic methodology with J. Dupuis. Neural network with M. Samuelides. Introduction to graphic models with G. Letac and A. de Falguerolles.

Master thesis : Supervised by P. Sarda and H. Cardot. First year of Master Degree in Theoretical Mathematics, with honors. Option Statistic. University Paul Sabatier, Toulouse III, France. Bachelor’s Degree in Theoretical Mathematics, with honors. University Paul Sabatier, Toulouse III, France.

1996/June 1998

Two-year university diploma, with honors. Option Mathematics et Computer Science. University Paul Sabatier, Toulouse III, France.

June 1998

A levels, with honors. Option Mathematics. Toulouse district, France.

Scientific award May 2005

Henri Philippart epidemiology prize award by InVS (Institut de Veille Sanitaire) and ADELF (Association Des Epidemiologistes De Langue Française). This prize (15000 euros), financed by the pharmaceutical firm GlaxoSmithKline, rewards a research project in epidemiology.

Computer Skills Operating systems Computing Languages Scientific softwares Office softwares

Windows 95/98/2000/XP, Linux, Unix. Pascal, HTML. Maple, Mathematica, Matlab, R, Splus, SAS. Word, Excel, Powerpoint, LATEX, Scientific workplace, Winedit.

Languages French English Spanish

mother tongue. working knowledge (University level). basic.

Teaching activities Oct 2005

- Lecture course in biostatistic (survival models, multi-states Markov models, semiMarkov models, informative censoring) for students in research master "calcul scientifique et bio mathématique". University of Ouagadougou (Burkina Faso). 20 students, 6 hours, responsible : G. Kientega.

2003/2004

- Tutorial in inferential statistics for students in bachelor’s degree of psychology. University Montpellier III. 40 students, 39 hours, responsible : C. Lavergne.

2002/2003

- Tutorial in probability and statistic for students in bachelor’s degree of psychology. University Montpellier III. 50 students, 22 hours, responsible : N. Molinari. - Tutorial in inferential statistics for students in bachelor’s degree of psychology. University Montpellier III. 40 students, 39 hours, responsible : C. Lavergne.

2001/2002

- Tutorial in inferential statistics for students in bachelor’s degree of psychology. University Montpellier III. 50 students, 20 hours, responsible : C. Lavergne. - Tutorial in descriptive statistics for students in first year university degree of sociology. University Montpellier III. 30 students, 9 hours, responsible : C. Lavergne.

PhD thesis PhD thesis in Biostatistic defended on the 29th April 2005 in University Montpellier I. Mention Très Honorable (highest distinction of the University). Title

Multi-states Markov models and application to asthma.

Advisors

Jean-Pierre DAURES, Professor of University Montpellier I Philippe GODARD, Professor of University Montpellier I

Jury

Catherine HUBER, Professor of University Paris V Michel AUBIER, Professor of University Paris VII Gilles DUCHARME, Professor of University Montpellier II Gérard TAP, Lecturer of University Toulouse III Abdelkader EL HASNAOUI, Biostatistician at GlaxoSmithKline

Abstract

In many fields, describing the evolution of the phenomena in time is of a capital interest, in particular to approach the problems of prediction and research for causal factors. In epidemiology, one has cohort data which inform about a group of patients followed in time. The multi-states Markov type models propose an interesting tool which makes it possible to study the evolution of a patient through the various stages of a disease. First of all, we recall the methodology relating to the homogeneous Markov model. This model is the least complex, it supposes that the intensities of transition between the states are constant in time. In the second time, we study a homogeneous semi-Markov model which supposes that the transition intensities depend on the time spent in the health state. The theory of counting processes is then presented in order to introduce a non-parametric estimation method within the framework of a non-homogeneous Markov model. In this model, the transition intensities depend on time since inclusion in the study. Most of the estimation methods suppose that the mechanism of censoring does not bring any information on the evolution of the disease. This assumption seldom being checked in practice, we propose an estimation method allowing to take into account an informative censoring. We also present a programmation guideline aiming to facilitate the implementation of the estimators based on counting processes. These methods are applied in order to study a data base of asthmatic patients. The objective is to help the clinicians with a better understanding of the disease evolution. The results make it possible to highlight the negative impact of overweight on the asthma evolution.

Keywords

Asthma, multi-states models, homogeneous and non-homogeneous Markov process, semiMarkov process, counting process, informative censoring.

Publications and presentations Statistics publications - Foucher Y., Mathieu E., Saint-Pierre P., Durand J.F., Daurès J.P. (2006). A semiMarkov model based on generalized weibull distribution with an illustration for HIV disease. Biometrical Journal. To appear. - Saint-Pierre P., Daurès J.P., Godard P. (2005). The analysis of asthma using homogeneous and non-homogeneous Markov models. Far East Journal of Theoretical Statistics, 16(1) :1-18. - Saint-Pierre P., Combescure C., Daurès J.P., Godard P. (2003). The analysis of asthma control under a Markov assumption with use of covariates. Statistics in Medicine, 22(24) :3755-70. Applied publications - Saint-Pierre P., Bourdin A., Chanez P., Daurès J.P., Godard P. (2006). Are overweighted asthmatics more difficult to control ? Allergy, 61(1) :79-84. - Combescure C., Chanez P., Saint-Pierre P., Daurès J.P., Proudhon H., Godard P. (2003). Variations in control of asthma over time can be assessed by a Markov model. European Respiratory Journal, 22(2) :298-304. Submitted articles - Foucher Y., Saint-Pierre P., Pugliese P., Dellamonica P., Daurès J.P. (Aout 2005). A semi-Markov frailty model for multistate survival data : illustration on HIV disease. Submitted in Lifetime Data Analysis. - Saint-Pierre P., Castelli C., Daurès J.P. (Mars 2005). Informative censoring in survival analysis and application to asthma. Submitted in Biometrical Journal. - Saint-Pierre P., Daurès J.P., Godard P. (Sept 2004). Implementation of semiparametric estimation in multi-state models. Submitted in Computer Methods and Programs in Biomedicine. Non-refereed contributions - Saint-Pierre P. (April 2005). PhD thesis, University Montpellier I. Multi-states Markov models and application to asthma (in French). - Saint-Pierre P., Daurès J.P., Godard P. (December 2003). I.N.S.E.R.M. activity report (Convention no 4AS04F). Analysis of epidemiological data (in French). - Saint-Pierre P. (June 2001). Master’s thesis, University Toulouse III. Generalized linear model for functional data and application to pollution forecasting (in French). - Saint-Pierre P. (June 2000). First year master’s thesis, University Toulouse III. Time series models with S-Plus software and application to meteorology (in French). Oral presentations - Saint-Pierre P. (2005). Multi-states Markov models - Informative censoring (in French). First young statisticians meeting organized by SFDS, Aussois, 30 August-2 September. - Saint-Pierre P., Daurès J.P., Godard P. (2004). Non-homogeneous Markov models (semi-parametric estimation) and application to asthma (in French). XXXVI th statistic meeting organized by SFDS, Montpellier, 24-28 May ; p100.

Publications and presentations (continued) Oral presentations (continued) - Saint-Pierre P., Chanez P., Daurès J.P., Godard P. (2004). Obesity : a risk factor for poor asthma control ? American Thoracic Society international conference, Orlando, 21-26 May. - Saint-Pierre P., Gras C., Daurès J.P., Godard P. (2003). Modelling of asthma evolution using homogeneous Markov model (in French). Conference of biometry and epidemiology, Lille, 15-16 September ; p 20-24. - Gras C., Saint-Pierre P., Daurès J.P., Trétarre B. (2003). Comparison of multi-states estimation methods for cancer prevalence (in French). Conference of biometry and epidemiology, Lille, 15-16 September ; p 106-108. - Mathieu E., Foucher Y., Saint-Pierre P., Dellamonica P.,Daurès J.P. (2003). Evaluation of HIV evolution (in French). Conference of biometry and epidemiology, Lille, 15-16 September ; p14-19. - Saint-Pierre P., Combescure C., Daurès J.P., Godard P. (2002). Modelling of asthma evolution using Markov models with covariates (in French). Journal of Epidemiology and Public Health, ADELF Conference, Toulouse, 18-20 September ; 50 : p 98. - Saint-Pierre P., Combescure C., Daurès J.P., Godard P. (2002). The analysis of asthma control under Markov assumption with use of covariates. 23rd Annual International Conference, International Society for Clinical Biostatistics, Dijon, France, 9-13 September ; p 45. Oral (guest) presentation - Saint-Pierre P., Daurès J.P., Godard P. (2003). The analysis of asthma control under Markov assumption. Workshop in Honor of Marvin Zelen. Probability, Statistics and Modelling in Public Health, 22-23 September. Statistic seminars - Saint-Pierre P. (2006). Multi-states Markov models (in French). Seminar, University Paris Dauphine, 6 January. - Saint-Pierre P. (2005). Multi-states models and application to asthma (in French). Seminar IURC, University Montpellier I, 15 April. - Saint-Pierre P. (2005). Markov models and asthma control evolution (in French). "Modèles Statistiques à Structure(s) Cachée(s)" group (French activity group on statistics), University Montpellier II, 7 April. - Saint-Pierre P. (2004). Dependant censoring in epidemiology (in French). Seminar IURC, University Montpellier I, 15 October. - Saint-Pierre P. (2004). Markov modelling in epidemiology (in French). Seminar IURC, University Montpellier I, 9 April. - Saint-Pierre P. (2001). Generalized linear model for functional data (in French). Seminar "statistic meeting of Agropolis, University Montpellier II, 3 June.